{"id":"W4403150254","doi":"10.1007/978-3-031-72111-3_25","title":"Enhancing New Multiple Sclerosis Lesion Segmentation via Self-supervised Pre-training and Synthetic Lesion Integration","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Computer science; Lesion; Segmentation; Artificial intelligence; Multiple sclerosis; Pattern recognition (psychology); Computer vision; Medicine; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006368831,0.0008409078,0.0005427496,0.0008188328,0.0002105275,0.0008806066,0.0006745767,0.0009750331,0.001431096],"category_scores_gemma":[0.001188856,0.0003687894,0.000740909,0.0006012704,0.0003412272,0.0005710394,0.0006838262,0.000594165,0.0009231476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003282627,"about_ca_system_score_gemma":0.000527481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001896877,"about_ca_topic_score_gemma":0.003392731,"domain_scores_codex":[0.9997868,0.00003252934,0.00001286926,0.00006296502,0.00007362092,0.00003124691],"domain_scores_gemma":[0.9994705,0.0001860136,0.00005613583,0.00007957225,0.0001776092,0.00003012154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004809355,0.0002382251,0.002660188,0.0003178927,0.0001666843,0.0003545809,0.0002292261,0.1842218,0.2324771,0.001981598,0.005063714,0.571808],"study_design_scores_gemma":[0.000008144066,0.0001087238,0.001705587,0.00001576955,0.00005039336,0.0004384002,0.00002816695,0.9322765,0.0617348,0.00125378,0.002362957,0.00001667909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1023168,0.0005757904,0.8905342,0.0001939974,0.0000882212,0.00009027877,0.0002740716,0.003623586,0.002302981],"genre_scores_gemma":[0.5202994,0.0004191691,0.4711916,0.0002008803,0.00008168075,0.00009716781,0.001280501,0.0007275101,0.005702037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001896877,"threshold_uncertainty_score":0.004787505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06337716415477536,"score_gpt":0.2686662085333482,"score_spread":0.2052890443785728,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}